© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7952
    Prev
    Next
    INDEX
    Explanations

    animals or wildlife

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кван
    0.46
    selfobj
    0.44
    keyValue
    0.44
     кризи
    0.43
    जनक
    0.41
     क्वांट
    0.40
    褰
    0.40
    जित
    0.40
    xcuserdatad
    0.40
    娌
    0.40
    POSITIVE LOGITS
     animals
    1.17
     animal
    1.07
     hayvan
    1.00
     Animals
    0.99
    Animals
    0.97
     animales
    0.96
     hewan
    0.95
    animals
    0.94
     animais
    0.93
     wildlife
    0.92
    Activations Density 0.406%

    No Known Activations